fix(ai): expose OpenRouter GLM-5.2 xhigh effort

closes #5770

packages/ai/CHANGELOG.md

@@ -8,6 +8,7 @@
 
 ### Fixed
 
+- Fixed OpenRouter GLM-5.2 metadata to expose `xhigh` reasoning and send OpenRouter's native `xhigh` effort ([#5770](https://github.com/earendil-works/pi/issues/5770)).
 - Fixed GitHub Copilot OAuth model availability to use the authenticated account's model picker catalog ([#5897](https://github.com/earendil-works/pi/issues/5897)).
 
 ## [0.79.8] - 2026-06-19

packages/ai/scripts/generate-models.ts

@@ -374,6 +374,9 @@ function applyThinkingLevelMetadata(model: Model<any>): void {
 		// Pi's low/medium/high pass through verbatim; OpenRouter normalizes to Mercury's vocabulary.
 		mergeThinkingLevelMap(model, { off: null });
 	}
+	if (model.provider === "openrouter" && model.id === "z-ai/glm-5.2") {
+		mergeThinkingLevelMap(model, { xhigh: "xhigh" });
+	}
 	if (model.provider === "opencode-go" && model.id === "kimi-k2.6") {
 		// OpenCode Go exposes Kimi K2.6 thinking as on/off, not distinct effort tiers.
 		mergeThinkingLevelMap(model, { minimal: null, low: null, medium: null });

packages/ai/src/models.generated.ts

@@ -4851,42 +4851,6 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 32768,
 		} satisfies Model<"google-generative-ai">,
-		"gemma-4-E2B-it": {
-			id: "gemma-4-E2B-it",
-			name: "Gemma 4 E2B IT",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			thinkingLevelMap: {"off":null,"minimal":"MINIMAL","low":null,"medium":null,"high":"HIGH"},
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"google-generative-ai">,
-		"gemma-4-E4B-it": {
-			id: "gemma-4-E4B-it",
-			name: "Gemma 4 E4B IT",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: true,
-			thinkingLevelMap: {"off":null,"minimal":"MINIMAL","low":null,"medium":null,"high":"HIGH"},
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"google-generative-ai">,
 	},
 	"google-vertex": {
 		"gemini-2.5-flash": {
@@ -9190,13 +9154,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.22,
+				input: 0.25,
-				output: 0.85,
+				output: 0.8,
 				cacheRead: 0.06,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262144,
+			maxTokens: 80000,
 		} satisfies Model<"openai-completions">,
 		"arcee-ai/trinity-mini": {
 			id: "arcee-ai/trinity-mini",
@@ -10573,13 +10537,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.67,
+				input: 0.66,
 				output: 3.5,
-				cacheRead: 0.2,
+				cacheRead: 0.33,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262144,
+			maxTokens: 262142,
 		} satisfies Model<"openai-completions">,
 		"moonshotai/kimi-k2.7-code": {
 			id: "moonshotai/kimi-k2.7-code",
@@ -10590,13 +10554,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.74,
+				input: 0.612,
-				output: 3.5,
+				output: 3.069,
-				cacheRead: 0.15,
+				cacheRead: 0.1296,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 16384,
+			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
 		"nex-agi/nex-n2-pro:free": {
 			id: "nex-agi/nex-n2-pro:free",
@@ -12761,13 +12725,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.066,
+				input: 0.063,
-				output: 0.26,
+				output: 0.21,
-				cacheRead: 0.029,
+				cacheRead: 0.021,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262144,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"thedrummer/rocinante-12b": {
 			id: "thedrummer/rocinante-12b",
@@ -13069,11 +13033,11 @@ export const MODELS = {
 			cost: {
 				input: 0.98,
 				output: 3.08,
-				cacheRead: 0.182,
+				cacheRead: 0.49,
 				cacheWrite: 0,
 			},
 			contextWindow: 202752,
-			maxTokens: 4096,
+			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
 		"z-ai/glm-5.2": {
 			id: "z-ai/glm-5.2",
@@ -13082,6 +13046,7 @@ export const MODELS = {
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
+			thinkingLevelMap: {"xhigh":"xhigh"},
 			input: ["text"],
 			cost: {
 				input: 1.2,
@@ -13203,13 +13168,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.67,
+				input: 0.66,
 				output: 3.5,
-				cacheRead: 0.2,
+				cacheRead: 0.33,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262144,
+			maxTokens: 262142,
 		} satisfies Model<"openai-completions">,
 		"~openai/gpt-latest": {
 			id: "~openai/gpt-latest",
@@ -15981,8 +15946,8 @@ export const MODELS = {
 			cost: {
 				input: 0.09,
 				output: 0.3,
-				cacheRead: 0,
+				cacheRead: 0.02,
-				cacheWrite: 0.02,
+				cacheWrite: 0,
 			},
 			contextWindow: 262114,
 			maxTokens: 262114,